| _app | | | 158 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | e177a908 |
| async_grpo_trainer.md | 12.3 kB | | f64e4edb |
| bco_trainer.html | 130 kB | | 43e2163f |
| bco_trainer.md | 14.1 kB | | 70d1d83a |
| bema_for_reference_model.html | 90 kB | | 51eb6411 |
| bema_for_reference_model.md | 7.18 kB | | e53a14ce |
| callbacks.html | 95.8 kB | | c6103021 |
| callbacks.md | 7.88 kB | | b0e1fbde |
| chat_template_utils.html | 46.2 kB | | bc7fe26d |
| chat_template_utils.md | 5.76 kB | | 9f289403 |
| chat_templates.html | 33.5 kB | | d65bacee |
| chat_templates.md | 6.03 kB | | 17d4c71e |
| clis.html | 53.4 kB | | 13cdc5cd |
| clis.md | 12.8 kB | | b7fe5b16 |
| community_tutorials.html | 31 kB | | 6d3ecb24 |
| community_tutorials.md | 10.9 kB | | 4b29ef42 |
| cpo_trainer.html | 144 kB | | c4f265ba |
| cpo_trainer.md | 23 kB | | 9d51b2a0 |
| customization.html | 30.9 kB | | f3b134b2 |
| customization.md | 4.04 kB | | 2989fb96 |
| data_utils.html | 62.7 kB | | e48f86ca |
| data_utils.md | 6.87 kB | | 23c743e6 |
| dataset_formats.html | 223 kB | | e228a82f |
| dataset_formats.md | 40.1 kB | | 1abefa84 |
| deepspeed_integration.html | 15.8 kB | | 75404e52 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 4aa03be2 |
| distillation_trainer.md | 12.3 kB | | ff7b44a9 |
| distributing_training.html | 96.5 kB | | d4f70f2a |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | cbc7b6ea |
| dpo_trainer.md | 30.7 kB | | d39ae0ee |
| example_overview.html | 42.7 kB | | 31ef8456 |
| example_overview.md | 19.6 kB | | 47255ab0 |
| experimental_overview.html | 10.8 kB | | 44af10bb |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | aa3250f5 |
| gfpo.md | 5.24 kB | | dc578b98 |
| gkd_trainer.html | 119 kB | | ba4c76e7 |
| gkd_trainer.md | 14.1 kB | | ed303e18 |
| gold_trainer.html | 166 kB | | 9c0d24a3 |
| gold_trainer.md | 18.1 kB | | 77beb444 |
| grpo_trainer.html | 561 kB | | c85828e0 |
| grpo_trainer.md | 55.8 kB | | cc1ca088 |
| grpo_with_replay_buffer.html | 90.3 kB | | b101d350 |
| grpo_with_replay_buffer.md | 6.16 kB | | acc1c45e |
| gspo_token.html | 50.2 kB | | 104e60ee |
| gspo_token.md | 4.27 kB | | 09d2ccd7 |
| index.html | 29 kB | | 915c3ff6 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d5edb01a |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 71a498d9 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | dd35071a |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | d0dc55e8 |
| kto_trainer.md | 18.3 kB | | bc91228f |
| liger_kernel_integration.html | 15 kB | | c582185a |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | 70c86f49 |
| llms.txt | 5.15 kB | | 4db17538 |
| lora_without_regret.html | 45 kB | | c41a3ccb |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 4545ac2c |
| merge_model_callback.md | 1.19 kB | | 9a9b062c |
| minillm_trainer.html | 180 kB | | 2b1a416a |
| minillm_trainer.md | 16.4 kB | | ffe2027b |
| nash_md_trainer.html | 125 kB | | 5bebdced |
| nash_md_trainer.md | 16.3 kB | | 71e77546 |
| nemo_gym.html | 58.5 kB | | 2334223b |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | bba3f5c0 |
| online_dpo_trainer.html | 180 kB | | 9f8fd638 |
| online_dpo_trainer.md | 23.1 kB | | 2776dcd4 |
| openenv.html | 114 kB | | ac49467e |
| openenv.md | 27.8 kB | | 28724bf0 |
| orpo_trainer.html | 127 kB | | 872c1052 |
| orpo_trainer.md | 17.7 kB | | a76cc724 |
| paper_index.html | 742 kB | | b1abe775 |
| paper_index.md | 19.1 kB | | 458502e4 |
| papo_trainer.html | 112 kB | | e2310855 |
| papo_trainer.md | 8.82 kB | | a17d5f9b |
| peft_integration.html | 131 kB | | 4f2afbbe |
| peft_integration.md | 23.9 kB | | 9ef37669 |
| ppo_trainer.html | 279 kB | | 825f525f |
| ppo_trainer.md | 41.4 kB | | 8a7079d8 |
| prm_trainer.html | 118 kB | | 593dad56 |
| prm_trainer.md | 13.9 kB | | 87f94ced |
| ptt_integration.html | 29.3 kB | | dce68fc8 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | a0b6275e |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 3ee01e2c |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 32e89f49 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|